]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 05e141a)
ggml-webgpu: Fix vectorized handling in mul-mat and mul-mat-id (#22578)
authorMasashi Yoshimura <redacted>
Fri, 1 May 2026 14:55:01 +0000 (23:55 +0900)
committerGitHub <redacted>
Fri, 1 May 2026 14:55:01 +0000 (07:55 -0700)
commitc3c15053925746c74fc2aaf6b864bd66665393c4
treec07fe5a0660981e84392b3224ff9fce2a0d3965dtree
parent05e141a6b34a1535096e2bb7828418df431f7efecommit | diff
ggml-webgpu: Fix vectorized handling in mul-mat and mul-mat-id (#22578)

* Fix vectorized condition of mul-mat-fast pipeline and add vectorized variant to mul-mat-id

* Apply suggestion from @CISC

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp diff | blob | history
Packaging of ggml-org/llama.cpp